laion-ai/erlich

a mask image for inpainting an init_image. white pixels = keep, black pixels = discard. resized to width = image width/8, height = image height/8

Seed for random number generator. If -1, a random seed will be chosen.

Number of diffusion steps to run. Due to PLMS sampling, using more than 100 steps is unnecessary and may simply produce the exact same output.

Target width

Target height

Your text prompt.

(optional) Negate the model's prediction for this text from the model's prediction for the target text.

Batch size. (higher = slower)

(optional) Initial image to use for the model's prediction. If provided alongside a mask, the image will be inpainted instead.

Classifier-free guidance scale. Higher values will result in more guidance toward caption, with diminishing returns. Try values between 1.0 and 40.0. In general, going above 5.0 will introduce some artifacting.

Aesthetic rating (1-9) - embed to use.

Aesthetic weight (0-1). How much to guide towards the aesthetic embed vs the prompt embed.

Fraction of sampling steps to skip when using an init image. Defaults to 0.0 if init_image is not specified and 0.5 if init_image is specified.

Whether to return intermediate outputs. Enable to visualize the diffusion process and/or debug the model. May slow down inference.